超参数优化

# !pip install neuralforecast hyperopt

from neuralforecast.utils import AirPassengersDF

Y_df = AirPassengersDF
Y_df.head()

from ray import tune
from neuralforecast.auto import AutoNHITS

nhits_config = AutoNHITS.get_default_config(h = 12, backend="ray")                      # Extract the default hyperparameter settings
nhits_config["random_seed"] = tune.randint(1, 10)                                       # Random seed
nhits_config["n_pool_kernel_size"] = tune.choice([[2, 2, 2], [16, 8, 1]])               # MaxPool's Kernelsize

nhits_config = {
       "max_steps": 100,                                                         # Number of SGD steps
       "input_size": 24,                                                         # Size of input window
       "learning_rate": tune.loguniform(1e-5, 1e-1),                             # Initial Learning rate
       "n_pool_kernel_size": tune.choice([[2, 2, 2], [16, 8, 1]]),               # MaxPool's Kernelsize
       "n_freq_downsample": tune.choice([[168, 24, 1], [24, 12, 1], [1, 1, 1]]), # Interpolation expressivity ratios
       "val_check_steps": 50,                                                    # Compute validation every 50 steps
       "random_seed": tune.randint(1, 10),                                       # Random seed
    }

from ray.tune.search.hyperopt import HyperOptSearch
from neuralforecast.losses.pytorch import MAE
from neuralforecast.auto import AutoNHITS

model = AutoNHITS(h=12,
                  loss=MAE(),
                  config=nhits_config,
                  search_alg=HyperOptSearch(),
                  backend='ray',
                  num_samples=10)

from neuralforecast import NeuralForecast

nf = NeuralForecast(models=[model], freq='M')
nf.fit(df=Y_df, val_size=24)

Global seed set to 8

results = nf.models[0].results.get_dataframe()
results.head()

Y_hat_df = nf.predict()
Y_hat_df = Y_hat_df.reset_index()
Y_hat_df.head()

Predicting DataLoader 0: 100%|██████████| 1/1 [00:00<00:00, 113.97it/s]

import optuna
optuna.logging.set_verbosity(optuna.logging.WARNING) # Use this to disable training prints from optuna

nhits_default_config = AutoNHITS.get_default_config(h = 12, backend="optuna")                   # Extract the default hyperparameter settings

def config_nhits(trial):
    config = {**nhits_default_config(trial)}
    config.update({
                   "random_seed": trial.suggest_int("random_seed", 1, 10), 
                   "n_pool_kernel_size": trial.suggest_categorical("n_pool_kernel_size", [[2, 2, 2], [16, 8, 1]])
                   })
    return config

def config_nhits(trial):
    return {
        "max_steps": 100,                                                                                               # Number of SGD steps
        "input_size": 24,                                                                                               # Size of input window
        "learning_rate": trial.suggest_loguniform("learning_rate", 1e-5, 1e-1),                                         # Initial Learning rate
        "n_pool_kernel_size": trial.suggest_categorical("n_pool_kernel_size", [[2, 2, 2], [16, 8, 1]]),                 # MaxPool's Kernelsize
        "n_freq_downsample": trial.suggest_categorical("n_freq_downsample", [[168, 24, 1], [24, 12, 1], [1, 1, 1]]),    # Interpolation expressivity ratios
        "val_check_steps": 50,                                                                                          # Compute validation every 50 steps
        "random_seed": trial.suggest_int("random_seed", 1, 10),                                                         # Random seed
    }

model = AutoNHITS(h=12,
                  loss=MAE(),
                  config=config_nhits,
                  search_alg=optuna.samplers.TPESampler(),
                  backend='optuna',
                  num_samples=10)

nf = NeuralForecast(models=[model], freq='M')
nf.fit(df=Y_df, val_size=24)

Global seed set to 6
Global seed set to 6
Global seed set to 1
Global seed set to 1
Global seed set to 7
Global seed set to 4
Global seed set to 9
Global seed set to 8
Global seed set to 7
Global seed set to 7
Global seed set to 6

results = nf.models[0].results.trials_dataframe()
results.drop(columns='user_attrs_ALL_PARAMS')

Y_hat_df_optuna = nf.predict()
Y_hat_df_optuna = Y_hat_df_optuna.reset_index()
Y_hat_df_optuna.head()

Predicting DataLoader 0: 100%|██████████| 1/1 [00:00<00:00, 112.75it/s]

import pandas as pd
import matplotlib.pyplot as plt

fig, ax = plt.subplots(1, 1, figsize = (20, 7))
plot_df = pd.concat([Y_df, Y_hat_df]).reset_index()

plt.plot(plot_df['ds'], plot_df['y'], label='y')
plt.plot(plot_df['ds'], plot_df['AutoNHITS'], label='Ray')
plt.plot(Y_hat_df_optuna['ds'], Y_hat_df_optuna['AutoNHITS'], label='Optuna')

ax.set_title('AirPassengers Forecast', fontsize=22)
ax.set_ylabel('Monthly Passengers', fontsize=20)
ax.set_xlabel('Timestamp [t]', fontsize=20)
ax.legend(prop={'size': 15})
ax.grid()